#MemRL
📰 MemRL outperforms RAG on complex agent benchmarks without fine-tuning

A new technique developed by researchers at Shanghai Jiao Tong University and other institutions enables large language model agents to learn new skills without the need for expensive fine-tuning....
MemRL outperforms RAG on complex agent benchmarks without fine-tuning
A new technique developed by researchers at Shanghai Jiao Tong University and other institutions enables large language model agents to learn new skills without the need for expensive fine-tuning....
venturebeat.com
January 22, 2026 at 6:55 PM
8/ CORE achieved these gains while adding far fewer context tokens: 37x less than RAG, 36x less than MemRL, and 1.4x less than GEPA.

Bottom line: CORE was more efficient than the baselines on each dimension: fewer rollouts, fewer training samples, and fewer added context tokens.
June 8, 2026 at 9:36 PM
7/ Using gpt-oss-120b as the base model, we found that CORE improved faster than GRPO, GEPA, episodic RAG, and MemRL across 4 different reasoning tasks.

In the 10-example train setting, CORE beat every baseline’s best result (after 1000s of rollouts) within its first 350 rollouts.
June 8, 2026 at 9:36 PM
MemRL just outpaced RAG on tough agent tests—no fine‑tuning needed. Think smarter memory, better Q‑values, and runtime learning on the fly. Curious how it beats the hype? Dive in! #MemRL #AgentBenchmarks #MemoryBank

🔗 aidailypost.com/news/memrl-b...
January 22, 2026 at 6:40 PM
Shengtao Zhang, Jiaqian Wang, Ruiwen Zhou, Junwei Liao, Yuchen Feng, Weinan Zhang, Ying Wen, Zhiyu Li, Feiyu Xiong, Yutao Qi, Bo Tang, Muning Wen
MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
https://arxiv.org/abs/2601.03192
January 7, 2026 at 9:18 PM
今日読んだ論文
MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
www.arxiv.org/abs/2601.03192

RAGの弱点を受動的なところだと見て、RAGに保存する情報に意図や結果、強化学習における行動価値のようなものを追加する。記憶の検索も類似度と価値を半分ずつ混ぜてランキングづけする。
ベンチマークとしてはHLE, BigCodeBench, ALFWorld, Lifelong Agent Benchが使われている
January 8, 2026 at 2:59 AM
[LLMs, AI, research]

MemRL actually looks really interesting: https://arxiv.org/html/2601.03192v1

It basically adds episodic memory to LLMs.

It achieves this by storing memories as sets of vectors, so rather than with Retrieval Augmented Generation which relies on textual queries, it actually […]
Original post on mastodon.derg.nz
mastodon.derg.nz
January 26, 2026 at 3:10 PM
MemRL outperforms RAG on complex agent benchmarks without fine-tuning

A new technique developed by researchers at Shanghai Jiao Tong University and other institutions enables large language model agents to learn new skills without the need for expensive fine-tuning. Researchers propose memrlA…
MemRL outperforms RAG on complex agent benchmarks without fine-tuning
A new technique developed by researchers at Shanghai Jiao Tong University and other institutions enables large language model agents to learn new skills without the need for expensive fine-tuning. Researchers propose memrlA framework that gives agents the ability to develop episodic memory, the ability to retrieve past experiences to create solutions to unseen tasks. MemRL allows agents to use environmental feedback to continuously refine their problem-solving strategies. MemRL is part of a broader effort to develop the research community continuous learning Capabilities for AI applications. In experiments on major industry benchmarks, the framework outperformed other baselines such as RAG and other memory organization techniques, especially in complex environments where exploration and experiments are required.
cnznews.com
January 22, 2026 at 8:34 PM
Zhang, Wang, Zhou, Liao, Feng, Zhang, Wen, Li, Xiong, Qi, Tang, Wen: MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory https://arxiv.org/abs/2601.03192 https://arxiv.org/pdf/2601.03192 https://arxiv.org/html/2601.03192
January 7, 2026 at 6:31 AM
CPU BRIGHT IDEAS LEE MEMRL: 2776 CLEVELAND AVE, FORT MYERS FL 33901-5855
May 25, 2026 at 12:09 PM